Content deleted Content added
Citation bot (talk | contribs) m Alter: pages. Add: issue. Formatted dashes. | You can use this bot yourself. Report bugs here. | User-activated. |
→Pros and cons: The resulting fitted function is not smooth (not differentiable along hinges). |
||
Line 314:
*The <code>earth</code>, <code>mda</code>, and <code>polspline</code> implementations do not allow missing values in predictors, but free implementations of regression trees (such as <code>rpart</code> and <code>party</code>) do allow missing values using a technique called surrogate splits.
*MARS models can make predictions quickly. The prediction function simply has to evaluate the MARS model formula. Compare that to making a prediction with say a [[Support Vector Machine]], where every variable has to be multiplied by the corresponding element of every support vector. That can be a slow process if there are many variables and many support vectors.
*The resulting fitted function is not smooth (not differentiable along hinges).
== Extensions and related concepts ==
| |||